skills/akiojin/skills/speckit-update/Gen Agent Trust Hub

speckit-update

Pass

Audited by Gen Agent Trust Hub on Sep 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill outlines a standard maintenance workflow for synchronizing local project files with updates from an upstream repository. The instructions are transparent and focus on configuration management.
  • [EXTERNAL_DOWNLOADS]: The workflow involves referencing and cloning the official GitHub Spec Kit repository (github.com/github/spec-kit). This is a well-known service, and the download is essential for the skill's stated purpose of providing updates.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill ingests external templates and scripts via git clone (SKILL.md).
  • Boundary markers: The workflow requires an initial status check ("現状把握") and a diff analysis ("差分取得") before any files are applied.
  • Capability inventory: The skill uses git clone, rg for searching, and standard file system writes.
  • Sanitization: The instructions explicitly mandate reviewing changes and re-applying local constraints, such as mandatory Japanese translation and strict ID formatting, which serves as a manual sanitization step.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 04:32 PM